Class Of Classification Research Articles

Investigating Remote Healthcare Accessibility with AI: Deep Learning and NLP-Based Knowledge Graph for Digitalized Diagnostics

Introduction: Recently, vast generational modern AI techniques have facilitated developments for accessing digital healthcare diagnosis with capabilities of detecting illnesses. Problem: There exists a lot of scepticism for e-health couple with high similarities on health symptoms which hinder text data analysis for remote diagnosis limiting remote services and affecting tech development. Objective: This research investigates and substantiates opportunities associated with computational leverage of text data analytics and cognitive extraction of knowledge insights to improve healthcare outcomes. Significance: The study presents an overview of public, an integrated deep learning (DL), and AI knowledge graph (KG) for healthcare accessibility of remote diagnostics with NLP assist. Method: This research applied both qualitative and quantitative analysis. Questionnaires were used to understand the computational analytics and cognitive extraction of AI knowledge graphs on healthcare data. Also, an AI model was built to detect, diagnose based on text data and streamline five (5) related disease symptoms for each given text input. Results: The result of the survey was tested with hypotheses of H1, H2, H3, H4, H5. Results show that deep learning models and knowledge graphs can effectively lead to a well-defined class of data classification. Our model also exhibits a tremendous level of acceptable prediction of health symptoms based on text data. The significant group was accepted as an identified health issue and the non-significant was identified as a non-health issue. Conclusion: The study concludes that a well-defined system based on a rigorous ethical healthcare standard can easily support determining a feasible remote diagnosis.

Study of the Anti-inflammatory Activity of 2-hydroxy-4-oxo-4-R-2-butenoates of Heterylammonium, which Have an Effect on the Blood Clotting System

Introduction. The use of anticoagulants is relevant in therapeutic, cardiological, neurological practice, geriatrics, obstetrics and gynecology, as well as in complications associated with COVID-19 infection and vaccination. In-depth studies of additional pleiotropic effects of existing anticoagulants are being conducted. The anti-inflammatory effect of heparins and direct oral anticoagulants was found. Special emphasis is placed on the existing close relationship between coagulation and inflammatory processes. The interaction of anticoagulants with nonsteroidal anti-inflammatory drugs when taken together is actively discussed. The combination of anticoagulant and anti-inflammatory action in one chemical molecule can solve the problem of polypragmasia.Aim. To study the anti-inflammatory activity of promising 2-hydroxy-4-oxo-4-R-2-butenoates of heterylammonium, which have an effect on the blood clotting system.Materials and methods. For further study of anti-inflammatory activity, 2-hydroxy-4-oxo-4-R-2-butenoates of heterylammonium, which have an effect on the blood clotting system, were selected. The anti-inflammatory effect was studied on a model of acute inflammatory edema in mongrel rats of both sexes weighing 180–250 g. The studied compounds were administered intragastrically. Diclofenac sodium and nimesulide substances administered similarly were used as comparison drugs. Acute toxicity of substances that showed activity was studied on white nonlinear mice of both sexes weighing 18–22 g with the definition of LD50.Results and discussion. All the studied 2-hydroxy-4-oxo-4-R-2-butenoates of heterylammonium have anti-inflammatory effects of varying severity. Data on the study of acute toxicity during intragastric administration, allow us to attribute the studied compounds to the 4.5 class of the hazard classification of chemical products.Conclusion. The anti-inflammatory activity of 14 2-hydroxy-4-oxo-4-R2-butenoates of heterylammonium has been studied. Five butanoate have an effect lower than comparison drugs, eight compounds are comparable to the effect of reference drugs, one compound is superior to nimesulide. The studied compounds can be assigned to class 4,5 of the hazard classification of chemical products. Medicinal candidates have been selected for further pharmacological, toxicological and technological study.

Analysis of Brain Tumor Detection Techniques

Abstract: The bio-medical image processing is the application of image processing to process medical data. The techniques of feature extraction and machine learning are efficient techniques brain tumor detection. Various network architectures are utilized, ordinarily with hundreds or thousands of adjustable parameters. The resulting condition forms are sufficiently general to unravel a large class of nonlinear classification and estimation problems and sufficiently complex to hide a multitude of sins. In this paper, various brain tumor detection techniques are reviewed analyzed in terms of certain parameters. It is analyzed that textual feature extraction and classification techniques give maximum accuracy for the brain tumor detection

Improved Classification of Handwritten Jawi Script Based on Main Part of Script Body

Since the entry of Islam, many ancient relics in the archipelago were written using Jawi script. Due to human or natural factors, these ancient relics will be damaged or destroyed. To avoid the loss of this ancient heritage data, the data must be stored in digital documents. In order to convert digital documents into machine-readable text format, the use of Optical Character Recognition (OCR) technology is inevitable. In this research, OCR technology is implemented on isolated Jawi scripts. Freeman Chain Code (FCC) is used to extract the isolated Jawi script features. Subsequently, the FCC feature is fed into Support Vector Machine (SVM) in order to classify the character. The decision rule classification is applied to the class of SVM classification in the Jawi script form. The results of the SVM classification into 19 classes reached 81.58%, while the results for merging into 15 classes produced better results with the accuracy 84.21%. Feature extraction of dot location is divided into the top, middle, and bottom. Feature extraction of the number of dotss is done by counting the number of dots, while feature extraction of the presence of holes is carried out by detecting the presence of holes in the characters. These features are applied to the class of results from SVM classification with decision-making rules. The percentage of success in applying the decision rules to the results of the classification of incorporation into 15 classes by SVM reached 92.86%. Further research will be conducted to determine the effect of the feature of the location of the dot and the number of dots on the shape of the main part of the character.

Study of the duration of the solar flare of the 23 and 24 solar cycles

Studying solar flares and their characteristics is significant for understanding the dynamics of the sun. In this work, a new view for studying the duration time of solar flares is presented. Regarding the analysis of the duration time, one of the solar flares parameters is introduced for the solar cycles 23 and 24. This is done by ordering the duration time of solar flares into five groups of minutes (<30, 30-60, 60 90, 90-120, >120) and calculating the total annual duration time of solar flares for each group. The total annual duration time is also calculated for each class of solar flare classification (B, C, M, X). Their relationship with both F10.7 and Kp-index are also studied. We found that approximately 41% of solar flares occur within 6-12 minutes for both solar cycles. Additionally, the total average of their duration time is 19.1 and 19.6 minutes, respectively.Also, the average duration time of the ascending phase is less than the descending phase of both solar cycles for all classes of solar flares, except for B-class, which is vice versa. The relationship between the duration time of solar flares with F10.7 is strong. In contrast, the relationship with the Earth’s magnetic field is weak.

Unknown Binary Protocol Recognition Algorithm Based on One Class of Classification and One‐Dimensional CNN

In order to solve the problem that there are a large number of unknown protocols on the network, which affect the network management and network security in varying degrees, an unknown binary protocol identification method is proposed. On the premise that the center cluster of unknown protocols is obtained by the clustering algorithm, the unknown protocols for network traffic are identified by combining one‐class of classification with one‐dimensional CNN classification technology. At first, a class of classification algorithm is used to select the unknown protocols, and then, the labeled protocol data obtained by clustering are used to train the one‐dimensional CNN model, and the classified binary protocol packets are directly used as the input of the one‐dimensional convolution neural network. After the classification of the CNN model, the unknown protocols are finally identified. The experimental results show that the proposed classification and recognition method is better than the traditional CNN and SVM algorithms, and the maximum frequency pooling is better than the traditional pooling method.

Erroneous Vehicle Velocity Estimation Correction Using Anisotropic Magnetoresistive (AMR) Sensors.

Magnetic field sensors installed in the road infrastructure can be used for autonomous traffic flow parametrization. Although the main goal of such a measuring system is the recognition of the class of vehicle and classification, velocity is the essential parameter for further calculation and it must be estimated with high reliability. In-field test campaigns, during actual traffic conditions, showed that commonly accepted velocity estimation methods occasionally produce highly erroneous results. For anomaly detection, we propose a criterion and two different correction algorithms. Non-linear signal rescaling and time-based segmentation algorithms are presented and compared for faulty result mitigation. The first one consists of suppressing the highly distorted signal peaks and looking for the best match with cross-correlation. The second approach relies on signals segmentation according to the feature points and multiple cross-correlation comparisons. The proposed two algorithms are evaluated with a dataset of over 300 magnetic signatures of a vehicle from unconstraint traffic conditions. Results show that the proposed criteria highlight all greatly faulty results and that the correction algorithms reduce the maximum error by twofold, but due to the increased mean error, mitigation technics shall be used explicitly with distorted signals.

The utility of hyperspectral imaging in patients with chronic venous disorders

ObjectiveThe underlying pathophysiology of lower limb changes in chronic venous disorders (CVD) may involve alteration in microcirculation and tissue oxygenation. Hyperspectral imaging (HSI) is a noninvasive tool that is used clinically to measure transcutaneous oxygenation in peripheral artery disease and diabetic foot disease. However, there has been little application in venous disease. The aim of this study was to determine if transcutaneous oxygenation in the lower limb, as measured by HSI, changes depending on the clinical component of the Clinical-Etiological-Anatomical-Pathophysiological (CEAP) classification in CVD. MethodsThis was an observational study of patients with CVD recruited from a vascular specialist clinic at a tertiary hospital from January 2020 to January 2021. Participants were allocated to eight groups according to the clinical component of CEAP classification of CVD. Baseline demographic and risk factor information were collected. Transcutaneous oxygenation was measured using HSI at seven sites around the foot and gaiter area in the supine and standing position. Participants rested supine for 15 minutes before the supine measurements and then stood for 15 minutes before the standing measurements. Tissue oxygenation was analyzed over a fixed circular surface area of 79 mm2 at the target location. Calculations of oxyhemoglobin level (artificial unit [AU]), deoxyhemoglobin level (AU), oxygen saturation (%), and temperature (°C) were obtained. The Northern Ethics Committee (18/NTA/78) approved this conduct of the study and participants signed written consent forms. ResultsThere were 94 participants (164 lower limbs) included in the study. The median age was 59 years and 59 participants (63%) were women. At all sites except the heel, deoxyhemoglobin measurements increased in the standing position compared with the supine position (P < .001). In the gaiter region, there was nearly a doubling in deoxyhemoglobin level at 5 cm above the medial malleolus (supine 43.88 AU vs standing 80.46 AU; P < .001) and 5 cm above the lateral malleolus (supine 46.33 AU vs standing 87.72 AU; P < .001). When measurements were stratified by clinical class of the CEAP classification, there was a greater increase in deoxyhemoglobin levels with increasing clinical class in the standing position (P < .001). This finding was not observed in the supine measurements. ConclusionsIn CVD, HSI shows an increase in deoxyhemoglobin in the standing compared with supine position, particularly in the gaiter region. Furthermore, standing deoxyhemoglobin increases as the CEAP clinical class increases. Thus, this noninvasive tool may respond to venous physiology and may supplement the clinical class of the CEAP classification system.

Assessment of the elderly population's health status as part of the clinical preventive services program

Human resources are regarded as a country's most valuable asset, and they play a critical role in economic development and growth. According to national policy, the elderly population is defined as 60 and up. Because of the rising demand for financial and social support due to health and related difficulties, the government is under pressure to adopt social policies for the elderly. Clinical preventive care can assist reduce the risks and expenses of chronic illness treatment and can prevent or delay disease onset. The aged population of either sex who visit a rural health geriatric centre's Outpatient department served as the study participants. Data were collected using a self-designed, pre-structured, and pre-validated questionnaire. The information was gathered in the form of a socio-demographic profile, which included all the necessary information, such as socioeconomic status, Body mass index (BMI), and personal habits. Visual examination, hearing, anaemia, musculoskeletal discomfort, diabetes mellitus, dermatological, hypertension, and female patients' reproductive disorders were all included in the clinical examination. A maximum of 263 (65.75%) of the subjects were in the age group of 60-69 years, 29.25% were labourers, and 38% were in modified BG Prasad class (III) of socioeconomic classification, 184 (46%) people had a BMI of 25-29.99 kg/m2. A total of 102 study participants (25.5%) had a chronic illness. 27.5% of the participants had hypertension, 11.8% had diabetes and coronary heart disease, 20.6% had hypertension and diabetes, and 10.8% had previously suffered from tuberculosis (TB). Hearing loss is a common complaint, and 5.5% reported issues with the genitourinary system, with nocturia accounting for 40.9%. The study participants, who were between the ages of 60 and 69, experienced a variety of chronic illnesses. The majority of the people in the study had hypertension, diabetes, heart disease, hypertension, diabetes, and a TB history.

A comparative analysis of text data classification accuracy and speed using neural networks, Bloom filter and naive Bayes

The object of research is the methods of fast classification for solving text data classification problems. The need for this study is due to the rapid growth of textual data, both in digital and printed forms. Thus, there is a need to process such data using software, since human resources are not able to process such an amount of data in full. A large number of data classification approaches have been developed. The conducted research is based on the application of the following methods of classification of text data: Bloom filter, naive Bayesian classifier and neural networks to a set of text data in order to classify them into categories. Each method has both disadvantages and advantages. This paper will reflect the strengths and weaknesses of each method on a specific example. These algorithms were comparatively among themselves in terms of speed and efficiency, that is, the accuracy of determining the belonging of a text to a certain class of classification. The work of each method was considered on the same data sets with a change in the amount of training and test data, as well as with a change in the number of classification groups. The dataset used contains the following classes: world, business, sports, and science and technology. In real conditions of the classification of such data, the number of categories is much larger than that considered in the work, and may have subcategories in its composition. In the course of this study, each method was analyzed using different parameter values to obtain the best result. Analyzing the results obtained, the best results for the classification of text data were obtained using a neural network.

BCDnet: Parallel heterogeneous eight-class classification model of breast pathology.

Breast cancer is the cancer with the highest incidence of malignant tumors in women, which seriously endangers women's health. With the help of computer vision technology, it has important application value to automatically classify pathological tissue images to assist doctors in rapid and accurate diagnosis. Breast pathological tissue images have complex and diverse characteristics, and the medical data set of breast pathological tissue images is small, which makes it difficult to automatically classify breast pathological tissues. In recent years, most of the researches have focused on the simple binary classification of benign and malignant, which cannot meet the actual needs for classification of pathological tissues. Therefore, based on deep convolutional neural network, model ensembleing, transfer learning, feature fusion technology, this paper designs an eight-class classification breast pathology diagnosis model BCDnet. A user inputs the patient's breast pathological tissue image, and the model can automatically determine what the disease is (Adenosis, Fibroadenoma, Tubular Adenoma, Phyllodes Tumor, Ductal Carcinoma, Lobular Carcinoma, Mucinous Carcinoma or Papillary Carcinoma). The model uses the VGG16 convolution base and Resnet50 convolution base as the parallel convolution base of the model. Two convolutional bases (VGG16 convolutional base and Resnet50 convolutional base) obtain breast tissue image features from different fields of view. After the information output by the fully connected layer of the two convolutional bases is fused, it is classified and output by the SoftMax function. The model experiment uses the publicly available BreaKHis data set. The number of samples of each class in the data set is extremely unevenly distributed. Compared with the binary classification, the number of samples in each class of the eight-class classification is also smaller. Therefore, the image segmentation method is used to expand the data set and the non-repeated random cropping method is used to balance the data set. Based on the balanced data set and the unbalanced data set, the BCDnet model, the pre-trained model Resnet50+ fine-tuning, and the pre-trained model VGG16+ fine-tuning are used for multiple comparison experiments. In the comparison experiment, the BCDnet model performed outstandingly, and the correct recognition rate of the eight-class classification model is higher than 98%. The results show that the model proposed in this paper and the method of improving the data set are reasonable and effective.

Modified Fuzzy Approach to Automatic Classification of Cyber Hate Speech from the Online Social Networks (OSN’s)

The extensive use of online media and sharing of data has given considerable benefits to humankind. Sentimental analysis has become the most dynamic and famous application area in current days, which is mainly used in knowing the public's opinion. Most algorithms of machine learning are used as principle methods for sentimental analysis. Even though several methods are available for classification and reviews, all of them belong to a single class of classification which differs among several different classes. No methods are available for the classifying of multi-class instances. Therefore, fuzzy methods are used for classifying the instances depended on multi-class for achieving a clear-cut view by indicating suitable labels to objects during the classification of text. This paper includes the categorization of cyberhate information. If there is a growth in dislike speeches of the online social network may lead to a worse impact amongst social activities, which causes tensions among communication and regional. So, there is the most demand for cyberhate conversation detection automatically through online social media. Generally, an updated process of fuzzy words is designed that includes two stages of training for the classification of cyberhate conversation into 4 forms, race, disability, sexual orientation, and religion. Depended on the types of classification, experiments have been conducted on these four forms by gathering different conversations through online media. Systems based on rules of fuzzy approach have been used. This fuzzy with rule-based is for the classification of features using Machine Learning techniques such as the words that implants for future bag-of-words and extraction methods. In this, the cyberhate conversations are taken from OSN's depended on the attributes defined in a dataset using rule-based fuzzy.

Minimum positive entropy of complex Enriques surface automorphisms

We determine the minimum positive entropy of complex Enriques surface automorphisms. This together with McMullen's work completes the determination of the minimum positive entropy of complex surface automorphisms in each class of Enriques-Kodaira classification of complex surfaces.

P2686Endothelial reaction mediates enhanced external counterpulsation effects in post-MI cardiac rehabilitation

Abstract Introduction The mechanisms mediating benefits of enhanced external counterpulsation (EECP) are disputable since the origin of the method. One of the possible explanations presumes increased diastolic flow leads to changes of endothelial function and plays a crucial role in alleviating the symptoms of angina and heart failure; the exact mechanisms of action are still under investigation, though the endothelial hypothesis possesses strong evidence. Purpose To reveal the impact of repeated EECP on endothelial function of patients undergoing cardiac rehabilitation program after myocardial infarction (MI) and to identify possible clinical implications of these changes. Methods The randomized sham-controlled study included 46 patients with coronary artery disease who suffered from ST-elevation MI (STEMI) 4–8 weeks prior to enrollment in 2017–2018. All patients had undergone primary PCI due to STEMI in 2–24 hours after the event. Echo parameters, exercise tolerance and the levels of ADMA and nitric oxide (NO) metabolites (total content, nitrite and nitrate) in plasma were determined at the enrollment stage and at three month follow-up. Patients were randomized and given 35 h of active counterpulsation (main group, n=24) or inactive counterpulsation (control group, n=22) over a six-week period after enrollment. Results The analysis showed no significant difference between groups at baseline: mean ejection fraction was 46% in the main group and 45% in the control group, no difference in exercise tolerance. The mean characteristics of endothelial function at baseline were similar in both main and control groups: total NO metabolites (17.3±2.14 μmol/L vs. 19.6±3.31, p=0. 42), nitrite level (0.76±0.17 μmol/L vs. 0.75±0.21, p=0. 36), ADMA level (0.78±0.15 μmol/L vs. 0.81±0.20, p=0. 22). At three month follow up 41,7% of patients of the main group showed improvement of one class of NYHA classification compared to 22,7% in the control group (U=122.3, p=0.012), agreed with improved exercise tolerance: average +2.8 MET in main group in opposite to only +0.8 MET in the controls (U=104, p=0.007). Control group demonstrated no significant dynamics of NO metabolites concentration comparing to baseline values, while in the main group there was a significant decrease of ADMA – 0.57±0.11 μmol/L (Z=r=−2.46, p=0.013) and increase of nitrite level – 1,12±0. 18 μmol/L (Z=r=−2.57, p=0.011), with no changes in total NO metabolites content. The further analysis demonstrated strong correlation between exercise capacity gain and ADMA decrease (R=r=−0.52, p=0.008) or nitrite elevation (R=0.48, p=0.012), with ADMA/nitrite ratio being the strongest predictor of clinical improvement (R=0.68, p=0.002). Conclusion Active EECP improves exercise capacity and heart failre symptoms in patients undergoing post-MI rehabilitation, with those effects being associated with endothelial function enhancement.

Learning Bayesian networks with local structure, mixed variables, and exact algorithms

Modern exact algorithms for structure learning in Bayesian networks first compute an exact local score of every candidate parent set, and then find a network structure by combinatorial optimization so as to maximize the global score. This approach assumes that each local score can be computed fast, which can be problematic when the scarcity of the data calls for structured local models or when there are both continuous and discrete variables, for these cases have lacked efficient-to-compute local scores. To address this challenge, we introduce a local score that is based on a class of classification and regression trees. We show that under modest restrictions on the possible branchings in the tree structure, it is feasible to find a structure that maximizes a Bayes score in a range of moderate-size problem instances. In particular, this enables global optimization of the Bayesian network structure, including the local structure. In addition, we introduce a related model class that extends ordinary conditional probability tables to continuous variables by employing an adaptive discretization approach. The two model classes are compared empirically by learning Bayesian networks from benchmark real-world and synthetic data sets. We discuss the relative strengths of the model classes in terms of their structure learning capability, predictive performance, and running time.

Ambulatory detection of sleep apnea using a non-contact biomotion sensor.

The high prevalence of obstructive sleep apnea has led to increasing interest in ambulatory diagnosis. The SleepMinder™ (SM) is a novel non-contact device that employs radiofrequency wave technology to assess the breathing pattern, and thereby estimate obstructive sleep apnea severity. We assessed the performance of SleepMinder™ in the home diagnosis of obstructive sleep apnea. One-hundred and twenty-two subjects were prospectively recruited in two protocols, one from an unselected sleep clinic cohort (n=67, mean age 51years) and a second from a hypertension clinic cohort (n=55, mean age 58years). All underwent 7 consecutive nights of home monitoring (SMHOME ) with the SleepMinder™ as well as inpatient-attended polysomnography in the sleep clinic cohort or cardiorespiratory polygraphy in the hypertension clinic cohort with simultaneous SleepMinder™ recordings (SMLAB ). In the sleep clinic cohort, median SMHOME apnea-hypopnea index correlated significantly with polysomnography apnea-hypopnea index (r=.68; p<.001), and in the hypertension clinic cohort with polygraphy apnea-hypopnea index (r=.7; p<.001). The median SMHOME performance against polysomnography in the sleep clinic cohort showed a sensitivity and specificity of 72% and 94% for apnea-hypopnea index ≥ 15. Device performance was inferior in females. In the hypertension clinic cohort, SMHOME showed a 50% sensitivity and 72% specificity for apnea-hypopnea index ≥ 15. SleepMinder™ classified 92% of cases correctly or within one severity class of the polygraphy classification. Night-to-night variability in home testing was relatively high, especially at lower apnea-hypopnea index levels. We conclude that the SleepMinder™ device provides a useful ambulatory screening tool, especially in a population suspected of obstructive sleep apnea, and is most accurate in moderate-severe obstructive sleep apnea.

Differences in classification for skin corrosion/irritation in EU and Ukraine: Case study of alternative (in vitro and in silico) methods application for classification of pesticide active ingredient imazamox

In Ukraine Globally Harmonized System of classification of chemicals has not been implemented yet. In this article we analyze differences between GHS/CLP classification systems and Hygienic Classification of Pesticides by the Degree of Hazard currently in force in Ukraine in respect of approach and criteria for classification of effects on skin. As a case study, we conducted in silico modelling of herbicide imazamox using skin irritation/corrosion modules of ToxTree. The prediction of ToxTree was “Not Corrosive to skin”. Then skin irritation and skin corrosion in vitro tests (OECD TGs 439, 431) were conducted. Classification of this substance based on in vitro and in vivo results according to GHS/CLP was the same, while it was not possible based on in vitro results to assign certain hazard class of Ukrainian classification due to difference in its and GHS/CLP criteria. However, ongoing process of harmonization of Ukrainian legislation with EU will give opportunity not only use alternative methods, but also adopt most recent advances and incorporate data from non-animal methods directly into classification criteria.

Clinico demographic profile of newly diagnosed HIV sero positive patients attending an ART centre: a cross sectional study

Background: India faces a high burden of HIV. An understanding of the determinants of this disease is of vital importance in curtailing this epidemic. The objective was to study the clinico-demographic profile of the study subject.Methods: This is a cross sectional study done on 142 patients which includes all newly diagnosed (diagnosed on or after 1st January 2012), sero positive, adult patients, enrolled at ART centre, Nalgonda and started on treatment during the months of December 2012, January 2013, February 2013. A pre designed, pre tested questionnaire was used. Data regarding their demographic characteristics and various clinical aspects was obtained. Results: Out of a total of 142 study subjects, majority (78.88%) belonged to economically productive age group (16-45 years). Married individuals constituted a majority (79.57%). A majority of the subjects were skilled laborers, belonged to lower middle class of BG Prasad classification, hailed from rural areas and belonged to nuclear families. Very few had high educational attainment. A majority (95.78%) reported not using condoms during their last sexual act and 9.16% subjects reported being previously diagnosed with an STD. Most common presenting complaint was fever and most common opportunistic infections were candidiasis and tuberculosis. Majority were found to belong to stage 1 HIV. Participants were mostly underweight and had severe anaemia. Majority had CD4 count between 201- 350 cells/mm3. Conclusions: Interventions targeting improvement in socio economic status, education levels, nutritional status as well as awareness about condom use must be built into the national HIV programme.

Endoscopic Stigmata: Recognition Lies in the Eye of the Beholder?

The most widely accepted classification for endoscopic stigmata is the Forrest classification, which divides endoscopically visible lesions into 3 classes (ie, I, II, and III). The classification is most useful because it is based on risk of rebleeding in the absence of endoscopic therapy. But how good are we at identifying/classifying the stigmata on endoscopy? Data from the REASON Registry from Canada, which reviewed endoscopy data retrospectively, showed that high-risk stigmata were present in 47.8% of the patients on endoscopy, but less than two-thirds of these received endoscopic therapy. On the other hand, about 9.8% patients with low-risk stigmata received endoscopic therapy. More than one-quarter of the reports did not document and classify the stigmata. Similar studies by Lau et al and Bour et al have shown poor inter-observer agreement between experts for recognition of endoscopic stigmata. An anonymous online survey was designed and separate links to the survey were e-mailed to faculty and fellows. We divided the survey into 2 parts—stigmata recognition and stigmata therapy. Under stigmata recognition, a standard image of a lesion belonging to one class of the Forrest classification was presented. The images were reproduced from records of our own endoscopies or from standard online digital libraries of endoscopic stigmata. The images were chosen to represent a very standard imagery representative of the lesion. Under stigmata therapy, we used different labeled images of endoscopic lesions and asked faculty/fellows to choose how they would treat the lesion endoscopically, including an option to not treat. Total of 17 faculty members and 11 fellows participated in the survey. Our study brings forth a few vital observations:1.Based on our data, overall low-risk stigmata was misclassified as high risk about 14% of time by board-certified gastroenterologists. This would have inadvertently led to unnecessary endoscopic therapy. In the same vein, high-risk stigmata was misclassified as low risk 6% of the time, putting patients at risk for rebleeding from them.2.Overall inter-observer agreement in recognition of stigmata was very good (κ = .85). It was poorest for an adherent clot (κ = .52) and best for spurting hemorrhage (κ = 1).3.Overall inter-observer agreement in treatment of endoscopic stigmata was good (κ = .74). It was again poorest for an adherent clot (κ = .58) and best for spurting hemorrhage/clean-based ulcer and flat pigmented spot (κ = 1).4.The κ indexes were significantly better for faculty with >3 years of experience vs junior fellows (first- and second-year fellows) (senior faculty overall κ = .85 ± .09 and junior fellows .68 ± .16; 2-tailed P = .047).

Diagnostic accuracy and prognostic significance of blood fibrosis tests and liver stiffness measurement by FibroScan in non-alcoholic fatty liver disease

NAFLD is highly prevalent but only a small subset of patients develop advanced liver fibrosis with impaired liver-related prognosis. We aimed to compare blood fibrosis tests and liver stiffness measurement (LSM) by FibroScan for the diagnosis of liver fibrosis and the evaluation of prognosis in NAFLD. Diagnostic accuracy was evaluated in a cross-sectional study including 452 NAFLD patients with liver biopsy (NASH-CRN fibrosis stage), LSM, and eight blood fibrosis tests (BARD, NAFLD fibrosis score, FibroMeter(NAFLD), aspartate aminotransferase to platelet ratio index (APRI), FIB4, FibroTest, Hepascore, FibroMeter(V2G)). Prognostic accuracy was evaluated in a longitudinal study including 360 NAFLD patients. LSM and FibroMeter(V2G) were the two best-performing tests in the cross-sectional study: AUROCs for advanced fibrosis (F3/4) were, respectively, 0.831±0.019 and 0.817±0.020 (p⩽0.041 vs. other tests); rates of patients with ⩾90% negative/positive predictive values for F3/4 were 56.4% and 46.7% (p<0.001 vs. other tests); Obuchowski indexes were 0.834±0.014 and 0.798±0.016 (p⩽0.036 vs. other tests). Two fibrosis classifications were developed to precisely estimate the histological fibrosis stage from LSM or FibroMeter(V2G) results without liver biopsy (diagnostic accuracy, respectively: 80.8% vs. 77.4%, p=0.190). Kaplan-Meier curves in the longitudinal study showed that both classifications categorised NAFLD patients into subgroups with significantly different prognoses (p<0.001): the higher was the class of the fibrosis classification, the worse was the prognosis. LSM and FibroMeter(V2G) were the most accurate of nine evaluated tests for the non-invasive diagnosis of liver fibrosis in NAFLD. LSM and FibroMeter(V2G) fibrosis classifications help physicians estimate both fibrosis stage and patient prognosis in clinical practice. The amount of liver fibrosis is the main determinant of the liver-related prognosis in patients with non-alcoholic fatty liver disease (NAFLD). We evaluated eight blood tests and FibroScan in a cross-sectional diagnostic study and found that FibroScan and the blood test FibroMeter(V2G) were the two most accurate tests for the non-invasive evaluation of liver fibrosis in NAFLD. A longitudinal prognostic study showed these two tests initially developed for the diagnosis are also prognostic markers as they allow for the stratification of NAFLD patients in several subgroups with significantly different prognosis.